What models are supported through this skill?

It supports the full range of foundation models available on Amazon Bedrock, including Anthropic Claude, Amazon Titan, Meta Llama, Mistral, and Stable Diffusion.

Can I use this skill to implement RAG?

Yes, the skill includes patterns for generating embeddings with Titan and using the Bedrock Agent Runtime for retrieve-and-generate (RAG) workflows.

How does this skill handle AWS permissions?

It includes best practices for IAM least privilege, providing JSON policy templates for bedrock:InvokeModel and other necessary data plane actions.

How do I enable specific models in Bedrock?

Models must be enabled via the AWS Management Console in specific regions by requesting access and accepting End User License Agreements (EULAs) where required.

Does this skill support streaming responses?

Yes, it provides implementation patterns for both synchronous invocation and real-time streaming using the invoke_model_with_response_stream API.

AWS Bedrock

Name: AWS Bedrock
Author: itsmostafa

byitsmostafa

•

963

Cloud Infrastructure

Integrates Amazon Bedrock foundation models to build generative AI applications with text, image, and embedding capabilities.

About

This skill empowers Claude to interact seamlessly with Amazon Bedrock, providing standardized patterns for invoking high-performance foundation models from top AI providers via a unified API. It offers deep technical guidance on implementing text generation, RAG patterns, and embeddings using both AWS CLI and Boto3, while covering essential operational aspects like model access configuration, cost optimization, and security best practices. Whether you are building serverless AI workflows or complex multi-turn conversational agents, this skill ensures your implementation follows AWS-recommended patterns for performance and reliability.

Key Features

963 GitHub stars
Comprehensive workflows for generating text embeddings and RAG patterns
Detailed CLI reference for model management and control plane operations
Implementation guides for streaming responses and multi-turn conversations
Security and cost optimization strategies including IAM policies and usage monitoring
Standardized patterns for invoking Claude, Titan, Llama, and Mistral models

Use Cases

Automating model access management and quota monitoring across AWS accounts
Implementing Retrieval-Augmented Generation (RAG) using Bedrock Knowledge Bases
Building serverless generative AI applications using AWS Lambda and Bedrock

About

Key Features

963 GitHub stars
Comprehensive workflows for generating text embeddings and RAG patterns
Detailed CLI reference for model management and control plane operations
Implementation guides for streaming responses and multi-turn conversations
Security and cost optimization strategies including IAM policies and usage monitoring
Standardized patterns for invoking Claude, Titan, Llama, and Mistral models

Use Cases

Automating model access management and quota monitoring across AWS accounts
Implementing Retrieval-Augmented Generation (RAG) using Bedrock Knowledge Bases
Building serverless generative AI applications using AWS Lambda and Bedrock